© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131074
    Prev
    Next
    INDEX
    Explanations

    contract, implementation, Islam, inspect, cubes

    np_acts-logits-general · gemini-2.5-flash-lite

    fade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     उम्मीदवार
    0.48
     कैंडिडेट्स
    0.48
     कैंडिडेट
    0.46
     interrupts
    0.46
     calendrier
    0.45
    र्ष
    0.44
     സ്ഥാന
    0.44
    .$;
    0.44
    Beacon
    0.43
     शक्त
    0.42
    POSITIVE LOGITS
    contro
    0.52
    ITZ
    0.51
    nameof
    0.49
    izia
    0.48
    ivité
    0.47
    obox
    0.47
    tion
    0.46
    isit
    0.45
    imte
    0.45
    leges
    0.44
    Activations Density 0.000%

    No Known Activations